Metadata-Version: 2.1
Name: concentration-lib
Version: 0.1.0
Summary: Library for concentration bounds
Home-page: https://github.com/sauxpa/concentration_lib
Author: Patrick Saux
Author-email: patrick.saux@ginria.fr
License: UNKNOWN
Platform: UNKNOWN
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: scipy

# Concentration bounds library

* concentration_bounds: marginal (non-uniform) bounds for bounded (Hoeffding, Bernstein, Bentkus...) and unbounded (sub-Gaussian Chernoff...) distributions.
* concentration_variance_bounds: marginal (non-uniform) bounds on the standard deviation process for bounded distributions.
* empirical_concentration_bounds: marginal bounds with data-dependent estimators rather than fixed parameters (e.g the variance in Bernstein bound is estimated from the data instead of being prior knowledge).
* uniform_concentration_bounds: sample size-uniform bounds (union, time-peeling, method of mixtures...).


